--- title: Kimi K3 Is Here: Efficient Day-0 Support on vLLM | daily.dev description: vLLM announces day-0 production support for Kimi K3, Moonshot AI's 2.8-trillion-parameter Mixture-of-Experts model with a 1M-token context window and native... canonical: https://daily.dev/posts/kimi-k3-is-here-efficient-day-0-support-on-vllm-6alao2vmf twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Kimi K3 Is Here: Efficient Day-0 Support on vLLM | daily.dev og:description: vLLM announces day-0 production support for Kimi K3, Moonshot AI's 2.8-trillion-parameter Mixture-of-Experts model with a 1M-token context window and native... og:url: https://daily.dev/posts/kimi-k3-is-here-efficient-day-0-support-on-vllm-6alao2vmf og:image: https://api.daily.dev/og/posts/6alaO2vMf.png og:image:alt: Kimi K3 Is Here: Efficient Day-0 Support on vLLM og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Kimi K3 Is Here: Efficient Day-0 Support on vLLM **[vLLM](https://daily.dev/sources/vllm)** · 22 min read · 3 upvotes · 0 comments ## Summary vLLM announces day-0 production support for Kimi K3, Moonshot AI's 2.8-trillion-parameter Mixture-of-Experts model with a 1M-token context window and native vision. Key highlights include: DSpark speculative decoding achieving 370 tok/s (3.14× speedup) on 16 NVIDIA GB300 GPUs; a redesigned hybrid prefix caching system that manages both recurrent KDA state and paged KV blocks; prefill/decode disaggregation with NIXL for large-scale deployments; sequence parallelism with custom reduce-scatter/all-gather kernels 1.7×–4.5× faster than NCCL; and multiple fused CUDA/Triton kernels for KDA decode, attention residuals, and LatentMoE tail fusion. The post covers architecture adaptations, deployment tips, benchmark results (0.976 GSM8K, 0.939 GPQA-Diamond), and a roadmap including Decode Context Parallelism and RL training support. NVIDIA Hopper/Blackwell and AMD MI355X are supported at launch. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#ai-inference](https://daily.dev/tags/ai-inference), [#vllm](https://daily.dev/tags/vllm), [#mixture-of-experts](https://daily.dev/tags/mixture-of-experts), [#kimi-k3](https://daily.dev/tags/kimi-k3) [View this post on daily.dev](https://daily.dev/posts/kimi-k3-is-here-efficient-day-0-support-on-vllm-6alao2vmf) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Kimi K3 Is Here: Efficient Day-0 Support on vLLM","url":"https://daily.dev/posts/kimi-k3-is-here-efficient-day-0-support-on-vllm-6alao2vmf","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/kimi-k3-is-here-efficient-day-0-support-on-vllm-6alao2vmf"},"datePublished":"2026-07-27T15:43:39.824Z","dateModified":"2026-07-27T15:44:05.829Z","description":"vLLM announces day-0 production support for Kimi K3, Moonshot AI's 2.8-trillion-parameter Mixture-of-Experts model with a 1M-token context window and native...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0c7a0f643ff20d95c7a62fa0bf2fe114?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0c7a0f643ff20d95c7a62fa0bf2fe114?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"vLLM","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"vLLM","logo":"https://media.daily.dev/image/upload/s--hTxEuls9--/f_auto/v1744613054/logos/vllm","url":"https://daily.dev/sources/vllm"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/kimi-k3-is-here-efficient-day-0-support-on-vllm-6alao2vmf","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-inference,vllm,mixture-of-experts,kimi-k3","timeRequired":"PT22M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"vLLM","item":"https://daily.dev/sources/vllm"},{"@type":"ListItem","position":3,"name":"Kimi K3 Is Here: Efficient Day-0 Support on vLLM"}]} ```